introduction
play

Introduction Dr. Ahmed Rafea CSCI485 Intelligent Agents 1 Chapter - PowerPoint PPT Presentation

Introduction Dr. Ahmed Rafea CSCI485 Intelligent Agents 1 Chapter Outline Artificial intelligence Internet and the Web Intelligent Agents Events, Conditions and Actions Agents and Human-Computer Interfaces Using Java for


  1. Introduction Dr. Ahmed Rafea CSCI485 Intelligent Agents 1

  2. Chapter Outline � Artificial intelligence � Internet and the Web � Intelligent Agents � Events, Conditions and Actions � Agents and Human-Computer Interfaces � Using Java for Intelligent Agents CSCI485 Intelligent Agents 2

  3. Artificial Intelligence � About 40 years old � What was hard for people and easy for computers was minimal compared to the things that were easy for people but almost impossible for computers CSCI485 Intelligent Agents 3

  4. Basic Concept � early idea included game playing and math after 40 years, there are 3 major phases of development: 1) early years: formal problems, emphasis was on creating general thinking machines 2) most successful AI projects aimed at very narrow problem domains and usually encoded much specific knowledge about the problem. Led to Expert Systems. 3) working on problems of human capabilities. The explosive growth in the internet and distributed computing has led to the idea of agents moving through the network and interacting with each other. � What do we mean by intelligence? An intelligent agent acts rationally, it does the things we would do, but not necessarily the same way. CSCI485 Intelligent Agents 4

  5. Symbol Processing Intelligence is � being able to recognize situations or cases � being able to learn from examples and generalize and apply that knowledge � to new situations Produce intelligent behaviour by manipulating symbols � A problem must be represented by a collection of symbols � Then appropriate algorithm developed to process symbols � Symbols are tokens representing real world objects or ideas � Ways to manipulate symbols: � use in if-then rules, processed using reasoning techniques called forward � and backward chaining construct a semantic network where the symbols and the concepts they � represent are connected by links into a network Use a frame in which related attributes are grouped together in a structure � and processed by a set of related procedures called daemons or fillers CSCI485 Intelligent Agents 5

  6. Neural networks (=Connectionism) � has more to do with how human or natural intelligence occurs � based on the architecture found in the brain � processes info by processing large amounts of raw data in a parallel manner � compared to symbol processing, they perform relatively low-level cognitive functions � knowledge gained through learning is stored in the connection weights and is not available for examination � ability to learn from surroundings is a crucial function CSCI485 Intelligent Agents 6

  7. The Internet and the Web � hyper text transfer protocol brought the internet from the realm of academia and computer technologists into the public consciousness � Knowing that the info is out there but not knowing how to find it is frustrating. There are popular search engines, but still web browsing is still a hit or miss proposition. � Here intelligent agents will emerge as truly useful personal assistants by searching, finding, and filtering info from the web. � B2B (business to business) and B2C (business to consumer) require intelligent software to provide personalized info to perform automated negotiations, and to perform planning and scheduling functions. CSCI485 Intelligent Agents 7

  8. Intelligent Agents � Change of focus in the AI research to apply basic AI to distributed systems, intranets and internet and web. � Initially the focus was limited to word searches, info retrieval and filtering. � As more commercial transactions are performed on networks, there is more interest in having smart agents that perform specific actions. CSCI485 Intelligent Agents 8

  9. Events, Conditions and Actions � How does the agent know that we want it to do something for us, or that it should respond to someone who is trying to contact us? � Deal with event, recognize condition and take action. � Events: anything that happens to change the environment or anything of which the agent should be aware. � Recognize Condition: after event, agent evaluates and recognizes what it means and responds to it. � Actions: do things for us. We must trust that our agent is going to behave rationally and in our best interest. CSCI485 Intelligent Agents 9

  10. Taxonomies of Agents � Agency: degree of autonomy that the software agent has in representing the user to other agents, applications and computers. � Intelligence: ability of the agent to capture and apply knowledge and processing to solve problems. � Mobility: ability to move between systems in a network which it introduces additional complexity because raises concerns about security and cost. CSCI485 Intelligent Agents 10

  11. Processing Strategies � Reactive of Reflex Agents: respond in the event condition action mode, do not have internal models of the world, respond only to external stimuli. They exhibit emergent behaviour , which is the result of simple agents where they share low level data rather than high level symbolic knowledge. � Deliberative or goal-directed Agents: have domain knowledge and planning ability necessary to take actions hoping to reach a certain goal. May cooperate with other agents to achieve tasks, and may use symbolic AI reasoning techniques. � Collaborative agents: work together to solve problems. Can solve large problems that are beyond the scope of a single agent, and allow modular approach based on specialization of agent functions or domain knowledge. CSCI485 Intelligent Agents 11

  12. Why use mobile agents? � reduce network load, because they move to a system and do their work there. � overcome network latency because resident on a machine rather than remote. � encapsulate protocols as they move around � operate autonomously � dynamically adapt to changes in system loading � are heterogeneous � are fault-tolerant since they move from a system that is faulty CSCI485 Intelligent Agents 12

  13. Processing Functions intelligent agent attributes can be combined and applied to a specific � domain to create a new, function-specific intelligent agent. Interface agents: work as personal assistants, employ learning to adapt � themselves Patti Maes (1994): four ways that learning can occur: � by watching over the user’s shoulder, observing what he does and imitating � him offer advice or take actions on the user’s behalf and then learn by receiving � feedback or reinforcement from the user get explicit instructions from the user � ask other agents for advice, and learn from their experience. � Information Agents: (deliver useful info to user) � help with the core problem of getting the right info at the right time. � They can be static or mobile. Agency and intelligence are the fundamental underlying capabilities on � which agents should be classified. CSCI485 Intelligent Agents 13

  14. Agents and Human-Computer Interfaces � Most natural way is through language, facial expression and body language. � Example: by IBM new project, gaze identification, where the user is looking on the screen. CSCI485 Intelligent Agents 14

  15. Using Java for Intelligent Agents � Overview of the Java Language � Autonomy � Intelligence � Mobility CSCI485 Intelligent Agents 15

  16. Overview of the Java language object-oriented � Developers of java originally intended to use C++ but needed a � language that could execute on different computer chips. ideal for programming on the internet � Java source code is compiled into an intermediate form called byte � codes which are stored in a class file and can be executed on any computer system than has Java Virtual Machine (JVM). Better than scripting language but slower than traditional languages � which are compiled directly. Just-In-Time compilers have developed for this purpose; they run � concurrently with JVM and determine what piece of code is called most frequently, which in turn are compiled into machine instructions on the fly so they do not need to be interpreted. Java applets are small java programs designed to be included in an � HTML document. Java is also a full function programming language that can be used to � write standalone applications CSCI485 Intelligent Agents 16

  17. Autonomy � Java applications are separate process and as such can be long running and autonomous. � They communicate with other programs using sockets. � Intelligent Agents are autonomous programs and are always waiting for user request or change in the environment. � In java there is an event processing mechanism used in the Abstract Windowing Toolkit (AWT) to pass user-defined events. CSCI485 Intelligent Agents 17

  18. Intelligence � Intelligence in intelligent agents can range from logic to reasoning and learning. � AI has two major aspects: knowledge representation and algorithms that manipulate them. Java can easily be used to implement them. CSCI485 Intelligent Agents 18

  19. Mobility � Java’s portability allows groups of java classes to be sent over a network and then executed on the target machine. � Java Applets provide a mechanism for running Java code remotely. � Some environments allow Java Processes to be started, suspended and moved. � JavaBean delegation event model allows dynamic registration of EventSources and Event Listeners. � The Java remote method invocation package allows Java objects to call methods on other objects across a network creating distributed object applications. CSCI485 Intelligent Agents 19

Recommend


More recommend